nature-ref-verifier

对学术文献逐条执行多源交叉验证，逐字段对比作者、标题、年份、卷期、页码，标记卷年/DOI年冲突、作者顺序异常、页码偏差等问题，输出结构化验证报告。可批量处理整篇论文/开题报告的参考文献列表，也可单条校验，支持与 Zotero 同步修正。

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/nature-ref-verifier/SKILL.md

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clearly sequenced, validation-backed workflow and well-structured progressive disclosure. The main weakness is conciseness: time-sensitive empirical stats and a large ASCII diagram add tokens that could be tightened or moved to a separate file.

Suggestions

Move the instance-specific empirical observations (the '35 条/7/9' stats, '2026 年实测') into references/common-patterns.md or a dedicated '实测经验' section to keep the main body lean.

Verify or create the referenced 'manifest.yaml' so the stated routing file actually exists in the bundle.

Consider replacing or shrinking the multi-line ASCII flow diagram with a compact bulleted pipeline to reduce token cost.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence without explaining basics, but embeds several time-sensitive empirical observations ('2026 年实测', '一次 35 条核查中 7/9 的错误属于此类', '35 条规模实测 3 个并行子代理') outside any deprecated/old-patterns section, plus a large ASCII diagram that could be trimmed.	3 / 5
Actionability	Provides fully executable guidance: concrete endpoints ('https://api.crossref.org/works/<DOI>'), named tools (pyzotero, zotero-mcp, kimi-datasource, webbridge), a field-level comparison matrix, specific error cases, an exact report format, and precise Zotero write paths (localhost:23119, --max-time, /connector/saveItems).	5 / 5
Workflow Clarity	Clear Step 1–5 sequence with explicit validation checkpoints (Step 2.0 DOI resolvability check, Step 3 severity-rated field comparison, Step 4 confidence assessment) and feedback/error-recovery loops (degradation strategies in '已知局限与应对'), satisfying the batch-operation validation requirement.	5 / 5
Progressive Disclosure	Good structure with a well-signaled one-level-deep reference ('需要处理批量差异…时，读取 references/common-patterns.md') and explicit load conditions; the referenced file exists. Minor gap: 'manifest.yaml' is mentioned as recording the routing but is not present in the bundle.	4 / 5
	Total	17 / 20 Passed

Description

67%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is highly specific and distinctive, clearly conveying what the skill does through concrete actions. Its main weakness is the absence of an explicit 'Use when…' trigger clause and natural-language trigger terms, which cap completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when…' clause (e.g. 'Use when submitting a paper, responding to reviewer comments about citations, or auditing a Zotero library') to satisfy the completeness 'when' requirement.

Surface natural trigger phrases such as '校验文献', 'check references', and '核对参考文献' into the description so users' actual wording matches the skill.

Include common synonyms/file extensions (e.g. '.bib', BibTeX) to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '逐条执行多源交叉验证', '逐字段对比作者、标题、年份、卷期、页码', '标记卷年/DOI年冲突、作者顺序异常、页码偏差', '输出结构化验证报告', '批量处理…参考文献列表', '单条校验', '支持与 Zotero 同步修正' — giving comprehensive coverage of capabilities.	5 / 5
Completeness	The 'what' is clear and detailed, but there is no 'Use when…' clause or equivalent explicit trigger guidance in the description, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Contains relevant domain keywords ('学术文献', '参考文献', '交叉验证', 'DOI', 'Zotero') but the natural trigger phrases users actually say ('校验文献', 'check references', '核对参考文献') live only in the body, not in the description, and synonyms are sparse.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (academic reference multi-source cross-validation with field-level conflict detection and Zotero sync) with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Yuan1z0825/nature-skills
Path: skills/nature-ref-verifier/SKILL.md
Commit: 3817cd1

Reviewed: about 8 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.